Cognitive Architecture to Composite Emotions from Autonomic Nervous System for Robotic Head

  • Charmasson Amandine
  • Kim Jong-Hwan
  • Kambiz Arab Tehrani
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 208)

Abstract

In this paper, methods are proposed for generating facial expression defined by Ekman’s facial expression database from a robotic head. This paper gives rise to how to generate two emotions at the same time and how to solve problems between two conflicting emotions. Among others, it uses a cognitive architecture and some biological values in generating several probabilities from the hidden Markov model. The cognitive architecture is characterized by three main parts: perception and decoding module for simulating brain system, thalamus, amygdala, hypothalamus and hippocampus; learning module to memorize the data and transmit the behavior of an emotion to the emotion module which will generate facial expression to the robotic head from a given environment. This paper presents two basic emotions, not only one as we have already tested. However, according to psychologists, some conflicts exist between emotions. This research develops a table of compatibility of emotions from the Robert Plutchik’s research, who is one of the precursors of emotional intelligence. To use Robert Plutchik’s Emotion database and Paul Ekman Emotion database, we decide to work with the 6 universal basic emotions, anger, disgust, fear, joy, sadness and surprise, which can be combined. The problem of conflicting composite emotion can be solved by using the properties of the biological stimuli. By this way, the composite emotion is made possible.

Keywords

Facial Expression Cognitive Architecture Composite Emotion Biological and Physiological brain System Hidden Markov Model 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Plutchik, R.: The Nature of Emotions. American Scientist (retrieved April 14, 2011)Google Scholar
  2. 2.
    Yoo, B.-S., Cho, S.-H., Kim, J.-H.: Fuzzy Integral-based Composite Facial Expression Generation for a Robotic Head. In: Proc. IEEE International Conference on Fuzzy Systems (June 2011)Google Scholar
  3. 3.
    Yoo, B.-S., Cho, S.-H., Kim, J.-H.: Facial Expression Generation Using Fuzzy Integral for Robotic Heads. In: Proc. FIRA Robot World Congress, Kaohsiung, Taiwan (August 2011)Google Scholar
  4. 4.
    Scherer, K.R., Wallbott, H.G.: Evidence for Universality and Cultural Variation of Differential Emotion Response Patterning. Journal of Personality and Social Psychology 66(2), 310–328 (1994)CrossRefGoogle Scholar
  5. 5.
    Scherer, K.R.: Psychological Models of Emotion, vol. 4(1), pp. 9–38 (1984)Google Scholar
  6. 6.
    Rabiner, L.R.: A Tutorial on Hidden Markov Models and Selected Application in Speech Recognition, Fellow. IEEEGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Charmasson Amandine
    • 1
  • Kim Jong-Hwan
    • 1
  • Kambiz Arab Tehrani
    • 2
  1. 1.Dept. of Electrical EngineeringKAISTDaejeonRepublic of Korea
  2. 2.Dept. of Embedded SystemESIGELECRouenFrance

Personalised recommendations